METHODS AND APPARATUS FOR POST-PROCESSING SPEECH RECOGNITION RESULTS OF RECEIVED RADIO VOICE MESSAGES ONBOARD AN AIRCRAFT

• US 20180174588A1
• Filed: 12/19/2016
• Published: 06/21/2018
• Est. Priority Date: 12/19/2016
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Agarwal, Jitender Kumar, Paulraj, Vasantha Selvi, Krishna, Kiran Gopala, Garg, Chaya, Burgin, Roger W., De Mers, Robert E
• Granted Patent: US 10,157,616 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G08G 5/0013 with a ground station
• CPC Class Codes: G08G 5/0021 located in the aircraft
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/221 Announcement of recognition results
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: G10L 25/69 for evaluating synthetic or decoded voice signals

Abstract

A method for displaying received radio voice messages onboard an aircraft is provided. The method post-processes, by at least one processor onboard the aircraft, a set of speech recognition (SR) hypothetical data to increase accuracy of an associated SR system, by: obtaining, by the at least one processor, secondary source data from a plurality of secondary sources; comparing, by the at least one processor, the set of SR hypothetical data to the secondary source data; and identifying, by the at least one processor, an aircraft tail number using the set of SR hypothetical data and the secondary source data; identifies, by the at least one processor, a subset of the received radio voice messages including the tail number; and presents, via a display device onboard the aircraft, the subset using distinguishing visual characteristics.

Claims

1. A method for displaying received radio voice messages onboard an aircraft, the method comprising:

post-processing, by at least one processor onboard the aircraft, a set of speech recognition (SR) hypothetical data to increase accuracy of an associated SR system, by;

obtaining, by the at least one processor, secondary source data from a plurality of secondary sources;

comparing, by the at least one processor, the set of SR hypothetical data to the secondary source data; and

identifying, by the at least one processor, an aircraft tail number using the set of SR hypothetical data and the secondary source data;

identifying, by the at least one processor, a subset of the received radio voice messages including the tail number; and

presenting, via a display device onboard the aircraft, the subset using distinguishing visual characteristics.

2. The method of claim 1, further comprising:

identifying a confidence level associated with the set of SR hypothetical data; and

when the confidence level does not exceed a predetermined threshold, completing the post-processing of the set of SR data.

3. The method of claim 1, further comprising:

establishing, via a wireless communication device, a communication connection to a server, wherein the plurality of secondary sources comprises the server; and

obtaining the secondary source data via the communication connection.

4. The method of claim 3, wherein the server stores at least one database including the secondary source data;

and

wherein the at least one database comprises at least one of an airline database, registration database, a manufacturer database, and an aircraft situation display to industry (ASDI) historical database.

5. The method of claim 1, wherein the plurality of secondary sources comprises at least an aircraft onboard transponder;

wherein the method further comprises obtaining current aircraft traffic information via the aircraft transponder; and

wherein the secondary source data comprises the current aircraft traffic information.

6. The method of claim 5, wherein the aircraft transponder comprises an Automatic Dependent Surveillance-Broadcast (ADS-B) device.

7. The method of claim 1, further comprising:

receiving, via a radio onboard the aircraft, a plurality of ground control messages comprising speech data; and

processing the speech data using a speech recognition (SR) device onboard the aircraft, to generate SR results, wherein the set of SR hypothetical data comprises the SR results.

8. The method of claim 1, further comprising:

comparing the set of SR hypothetical data to stored identifying information associated with the aircraft;

determining a confidence level associated with accuracy of the set of SR hypothetical data; and

performing the post-processing step when the confidence level is not greater than a predetermined threshold.

9. A system for displaying radio voice messages received onboard an aircraft, the system comprising:

system memory;

an aircraft onboard radio, configured to receive the radio voice messages onboard the aircraft;

a display device, configured to present transcriptions of the radio voice messages received onboard the aircraft; and

at least one processor, communicatively coupled to the system memory, the aircraft onboard radio, and the display device, the at least one processor configured to;

perform post-processing for a set of speech recognition (SR) hypothetical data to increase accuracy of an associated SR system, by;

obtaining secondary source data from a plurality of secondary sources;

comparing the set of SR hypothetical data to the secondary source data; and

identifying an aircraft tail number using the set of SR hypothetical data and the secondary source data;

identify a subset of the received radio voice messages including the tail number; and

initiate presentation, via the display device, of the subset using distinguishing visual characteristics.

10. The system of claim 9, wherein the at least one processor is further configured to:

identify a confidence level associated with the set of SR hypothetical data; and

when the confidence level does not exceed a predetermined threshold, complete the post-processing of the set of SR data.

11. The system of claim 9, further comprising a wireless communication device communicatively coupled to the at least one processor, the wireless communication device configured to:

establish a communication connection to a server, wherein the plurality of secondary sources comprises the server; and

obtain the secondary source data via the communication connection.

12. The system of claim 11, wherein the server stores at least one database including the secondary source data;

and

wherein the at least one database comprises at least one of an airline database, registration database, a manufacturer database, and an aircraft situation display to industry (ASDI) historical database.

13. The system of claim 9, wherein the plurality of secondary sources comprises at least an aircraft onboard transponder;

wherein the at least one processor is further configured to obtain current aircraft traffic information via the aircraft transponder; and

wherein the secondary source data comprises the current aircraft traffic information.

14. The system of claim 9, wherein the radio voice messages comprise speech data;

and

wherein the system of claim 9 further comprises a speech recognition (SR) device onboard the aircraft, wherein the SR device is communicatively coupled to the aircraft onboard radio and the at least one processor, and wherein the SR device is configured to process the speech data to generate SR results, wherein the set of SR hypothetical data comprises the SR results.

15. The system of claim 9, wherein the at least one processor is further configured to:

compare the set of SR hypothetical data to stored identifying information associated with the aircraft to locate a match;

determining a confidence level associated with accuracy of the set of SR hypothetical data; and

perform the post-processing step when the confidence level is not greater than a predetermined threshold.

16. A non-transitory, computer-readable medium containing instructions thereon, which, when executed by a processor, perform a method comprising:

receiving a radio communication onboard a first aircraft, the radio communication comprising a set of speech recognition data;

comparing the set of speech recognition data to a stored identifier for the first aircraft;

determining a confidence level associated with accuracy of the set of SR hypothetical data; and

when the confidence level is not greater than a predetermined threshold, performing post-processing of the set of speech recognition data by;

obtaining secondary source data associated with a plurality of aircraft comprising at least the first aircraft;

comparing the speech recognition data to the secondary source data;

identifying the stored identifier, based on the comparing; and

determining that the radio communication is associated with the first aircraft, based on identifying the stored identifier; and

presenting, via a display device onboard the aircraft, a plurality of radio communications associated with the first aircraft using distinguishing visual characteristics, wherein the plurality of radio communications comprises the radio communication.

17. The non-transitory, computer-readable medium of claim 16, wherein the method further comprises:

identifying a confidence level associated with the set of speech recognition data; and

when the confidence level does not exceed a predetermined threshold, completing the post-processing of the set of speech recognition data.

18. The non-transitory, computer-readable medium of claim 16, wherein the method further comprises:

establishing, via a wireless communication device, a communication connection to a server, wherein the plurality of secondary sources comprises the server; and

obtaining the secondary source data via the communication connection.

19. The non-transitory, computer-readable medium of claim 18, wherein the server stores at least one database including the secondary source data;

and

wherein the at least one database comprises at least one of an airline database, registration database, a manufacturer database, and an aircraft situation display to industry (ASDI) historical database.

20. The non-transitory, computer-readable medium of claim 16, wherein the plurality of secondary sources comprises at least an aircraft onboard transponder;

wherein the method further comprises obtaining current aircraft traffic information via the aircraft transponder; and

wherein the secondary source data comprises the current aircraft traffic information.